A bio- medical Question Answering system for the Malayalam language using word embedding and Bidirectional Encoder Representation from Transformers.

Natural language inference (NLI) is an essential subtask in many natural language processing applications. It is a directional relationship from premise to hypothesis. A pair of texts is defined as entailed if a text infers its meaning from the other text. The NLI is also known as textual entailment recognition, and it recognizes entailed and contradictory sentences in various NLP systems like Question Answering, Summarization and Information retrieval systems. This paper describes the NLI problem attempted for a low resource Indian language Malayalam, the regional language of Kerala. More than 30 million people speak this language. The paper is about the Malayalam NLI dataset, named MaNLI dataset, and its application of NLI in Malayalam language using different models, namely Doc2Vec (paragraph vector), fastText, BERT (Bidirectional Encoder Representation from Transformers), and LASER (Language Agnostic Sentence Representation). Our work attempts NLI in two ways, as binary classification and as multiclass classification. For both the classifications, LASER outperformed the other techniques. For multiclass classification, NLI using LASER based sentence embedding technique outperformed the other techniques by a significant margin of 12% accuracy. There was also an accuracy improvement of 9% for LASER based NLI system for binary classification over the other techniques.

Fenomena bullying di media sosial, khususnya di Twitter, telah menjadi isu yang semakin memprihatinkan dengan dampak signifikan terhadap kesehatan mental pengguna. Dalam rangka mengatasi masalah ini, deteksi otomatis tweet yang mengandung konten bullying menjadi sangat penting. Penelitian ini bertujuan untuk membandingkan performa dua model pemrosesan bahasa alami terbaru, yaitu BERT (Bidirectional Encoder Representations from Transformers) dan XLNet, dalam klasifikasi tweet yang mengandung bullying. Metodologi penelitian ini melibatkan pengumpulan dataset tweet yang telah dilabeli sebagai bullying atau non-bullying. Proses preprocessing teks dilakukan untuk membersihkan dan menyiapkan data sebelum digunakan dalam pelatihan model. Kedua model, BERT dan XLNet, dilatih dan diuji menggunakan dataset yang sama. Evaluasi performa dilakukan dengan menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa kedua model memiliki kemampuan yang baik dalam mengidentifikasi tweet bullying, akan tetapi XLNet menunjukkan performa yang lebih unggul dibandingkan BERT dengan tingkat akurasi sebesar 95%. Dengan nilai presisi = 100%, recall = 0,87%, dan F1-score = 0,88%. XLNet mampu menangkap konteks dan nuansa bahasa yang lebih kompleks dalam tweet, yang berkontribusi pada akurasi klasifikasi yang lebih tinggi. Penelitian ini memberikan kontribusi penting dalam bidang deteksi bullying di media sosial dengan menunjukkan bahwa penggunaan model XLNet lebih efektif dibandingkan BERT. Temuan ini dapat membantu platform seperti Twitter dalam mengidentifikasi dan mencegah konten bullying, sehingga menciptakan lingkungan online yang lebih aman bagi pengguna, serta dapat digunakan sebagai dasar untuk pengembangan sistem deteksi bullying yang lebih canggih dan efisien di masa depan. Abstract The phenomenon of bullying on social media, particularly on Twitter, has become an increasingly concerning issue with significant impacts on users' mental health. In order to address this issue, automatic detection of tweets containing bullying content is crucial. This study aims to compare the performance of two recent natural language processing models, namely BERT (Bidirectional Encoder Representations from Transformers) and XLNet, in the classification of tweets containing bullying. The research methodology involves collecting a dataset of tweets that have been labelled as bullying or non-bullying. Text preprocessing is done to clean and prepare the data before it is used in model training. Both models, BERT and XLNet, were trained and tested using the same dataset. Performance evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results show that both models have a good ability to identify bullying tweets, but XLNet shows superior performance compared to BERT with an accuracy rate of 95%. With precision = 100%, recall = 0.87%, and F1-score = 0.88%. XLNet is able to capture more complex context and language nuances in tweets, which contributes to higher classification accuracy. This research makes an important contribution to the field of bullying detection on social media by showing that the use of the XLNet model is more effective than BERT. These findings can help platforms like Twitter identify and prevent bullying content, thereby creating a safer online environment for users, and can be used as a basis for the development of more sophisticated and efficient bullying detection systems in the future.

To address the insufficient expressive capabilities of traditional methods in assessing the development level of rural tourism, this study explores the fusion application of the Bidirectional Encoder Representations from Transformers (BERT) and the Back Propagation (BP) algorithm to enhance the accuracy and comprehensiveness of rural tourism development assessment. Firstly, this study introduces the BERT deep learning model and its applications in natural language processing, alongside the role of the BP algorithm in pattern recognition and predictive analysis. Subsequently, a framework for assessing rural tourism development levels, integrating BERT and the BP algorithm, is proposed. This framework collects multidimensional rural tourism-related data and utilizes the BERT model for sentiment analysis and topic extraction from textual data. Empirical analysis of rural tourism development in a specific region validates the effectiveness of the proposed approach. Experimental results demonstrate: (1) The model achieves an accuracy of 84.33% and an F1 score of 85.33% on the publicly available Laptop dataset, with a processing time of 20 s, significantly outperforming other methods. Compared to traditional approaches, the proposed method accurately captures correlations between textual information and numerical data, thereby enhancing the credibility and accuracy of assessment results. (2) From the ablation study results, it is evident that removing any component from the model leads to performance degradation. Specifically, removing the Bidirectional Gated Recurrent Unit (BiGRU) reduces accuracy and F1 scores to 78.21% and 76.33% on the Laptop dataset, and to 85.10% and 70.45% on the Tourist_F dataset. Removing Text Convolutional Neural Network (CNN) reduces accuracy and F1 scores to 79.34% and 77.56% on the Laptop dataset, and to 86.25% and 72.11% on the Tourist_F dataset. The most significant performance decline occurs upon removing BERT, with accuracy and F1 scores decreasing to 70.14% and 66.43% on the Laptop dataset, and to 78.45% and 60.33% on the Tourist_F dataset. These results indicate that BiGcRU, TextCNN, and BERT each contribute significantly to the model’s performance. This study provides substantial support for advancing sustainable development in rural tourism, offering significant practical and innovative value.

Emails are the simplest way to communicate between users. But increasing rate of cybercrime activities require shrewd use of email. Phishing email is one of the most perilous threats nowadays. Through phishing email, attackers want to steal the sensitive information of the email users. This sensitive information includes username, password, credit card details etc. These may cause excessive financial loss. Many anti-phishing methods exist in literature to detect phishing emails. But criminals use new methods day by day, which causes challenge to build anti-phishing methods to prevent phishing emails. In this paper the performance of two deep learning models for detection of phishing email have been compared. The first model uses convolution neural network with Global Vector (GloVe) word embedding where Bidirectional Encoder Representations from Transformers (BERT) model with fine tuning has been used in second model. The proposed method detects the phishing email by analyzing the content of the email. Some widely used datasets (lingSpam, enronSpamSubset, completeSpamAssassin, Jose Nazario's phishing dataset and Enron email dataset) are merged together and applied to measure the performance of the model. It is found that the GloVe word embedding achieves better accuracy (98%) than BERT model (96%) in detection of phishing emails in the present context.

With the popularity of large-scale corpora, statistics-based models have become mainstream model in Natural Language Processing (NLP). The Bidirectional Encoder Representations from Transformers (BERT), as one of those models, has achieved excellent results in various tasks of NLP since its emergence. But it still has shortcomings, such as poor capability of extracting local features and exploding of training gradients. After analyzing the shortcomings of BERT, this paper proposed an Information-gain Association Vector Semi-supervised Bidirectional Encoder Representations from Transformers (IAS-BERT) model, which improves the capability of capturing local features. Considering the influence of feature's polarity to overall sentiment and association between two word-embeddings, we use information gain on the training corpus. And then, the information gain results are used as an annotation of training corpus to generate a new word embedding. At the same time, we use forward-matching to optimize the computational overhead of IAS-BERT. We experiment the model on dataset of sentiment analysis, and it have achieved good results.

BackgroundIt is essential for radiologists to communicate actionable findings to the referring clinicians reliably. Natural language processing (NLP) has been shown to help identify free-text radiology reports including actionable findings. However, the application of recent deep learning techniques to radiology reports, which can improve the detection performance, has not been thoroughly examined. Moreover, free-text that clinicians input in the ordering form (order information) has seldom been used to identify actionable reports. This study aims to evaluate the benefits of two new approaches: (1) bidirectional encoder representations from transformers (BERT), a recent deep learning architecture in NLP, and (2) using order information in addition to radiology reports.MethodsWe performed a binary classification to distinguish actionable reports (i.e., radiology reports tagged as actionable in actual radiological practice) from non-actionable ones (those without an actionable tag). 90,923 Japanese radiology reports in our hospital were used, of which 788 (0.87%) were actionable. We evaluated four methods, statistical machine learning with logistic regression (LR) and with gradient boosting decision tree (GBDT), and deep learning with a bidirectional long short-term memory (LSTM) model and a publicly available Japanese BERT model. Each method was used with two different inputs, radiology reports alone and pairs of order information and radiology reports. Thus, eight experiments were conducted to examine the performance.ResultsWithout order information, BERT achieved the highest area under the precision-recall curve (AUPRC) of 0.5138, which showed a statistically significant improvement over LR, GBDT, and LSTM, and the highest area under the receiver operating characteristic curve (AUROC) of 0.9516. Simply coupling the order information with the radiology reports slightly increased the AUPRC of BERT but did not lead to a statistically significant improvement. This may be due to the complexity of clinical decisions made by radiologists.ConclusionsBERT was assumed to be useful to detect actionable reports. More sophisticated methods are required to use order information effectively.

With the increasing number of web texts, the classification of web texts has become an important task. In this paper, the text word vector representation method is first analyzed, and bidirectional encoder representations from transformers (BERT) are selected to extract the word vector. The bidirectional gated recurrent unit (BiGRU), convolutional neural network (CNN), and attention mechanism are combined to obtain the context and local features of the text, respectively. Experiments were carried out using the THUCNews dataset. The results showed that in the comparison between word-to-vector (Word2vec), Glove, and BERT, the BERT obtained the best classification result. In the classification of different types of text, the average accuracy and F1 value of the BERT-BGCA method reached 0.9521 and 0.9436, respectively, which were superior to other deep learning methods such as TextCNN. The results suggest that the BERT-BGCA method is effective in classifying web texts and can be applied in practice.

Bidirectional Encoder Representations from Transformers (BERT) and BERT-based approaches are the current state-of-the-art in many natural language processing (NLP) tasks; however, their application to document classification on long clinical texts is limited. In this work, we introduce four methods to scale BERT, which by default can only handle input sequences up to approximately 400 words long, to perform document classification on clinical texts several thousand words long. We compare these methods against two much simpler architectures - a word-level convolutional neural network and a hierarchical self-attention network - and show that BERT often cannot beat these simpler baselines when classifying MIMIC-III discharge summaries and SEER cancer pathology reports. In our analysis, we show that two key components of BERT - pretraining and WordPiece tokenization - may actually be inhibiting BERT's performance on clinical text classification tasks where the input document is several thousand words long and where correctly identifying labels may depend more on identifying a few key words or phrases rather than understanding the contextual meaning of sequences of text.

We study the problem of incorporating prior knowledge into a deep Transformer-based model,i.e.,Bidirectional Encoder Representations from Transformers (BERT), to enhance its performance on semantic textual matching tasks. By probing and analyzing what BERT has already known when solving this task, we obtain better understanding of what task-specific knowledge BERT needs the most and where it is most needed. The analysis further motivates us to take a different approach than most existing works. Instead of using prior knowledge to create a new training task for fine-tuning BERT, we directly inject knowledge into BERT's multi-head attention mechanism. This leads us to a simple yet effective approach that enjoys fast training stage as it saves the model from training on additional data or tasks other than the main task. Extensive experiments demonstrate that the proposed knowledge-enhanced BERT is able to consistently improve semantic textual matching performance over the original BERT model, and the performance benefit is most salient when training data is scarce.

In this paper we focus on an Natural Language Inference task. Being given two sentences, we classify their relation as NEUTRAL, ENTAILMENT or CONTRADICTION. Considering the achievements of BERT (Bidirectional Encoder Representations from Transformers) in many Natural Language Processing tasks, we use BERT features to create our base model for this task. However, several questions arise: can other features improve the performance obtained with BERT? If we are able to predict the situations in which BERT will fail, can we improve the performance by providing alternative models for these situations? We test several strategies and models, as alternatives to the standalone BERT model in the possible failure situations, and we take advantage of semantic features extracted from Discourse Representation Structures.

Transformer-based architectures have significantly advanced Natural Language Processing (NLP), with Bidirectional Encoder Representations from Transformers (BERT) serving as a strong baseline for extractive Question Answering (QA). This study aims to evaluate the performance of Indonesian BERT models on extractive QA tasks and to identify the most effective model for low-resource language settings. This research employed a comparative experimental method using two Indonesian BERT variants: indobert-base- ncased (IndoLEM) and indobert-base-p1 (IndoNLU/IndoBenchmark). Both models were fine-tuned on an Indonesian version of SQuAD 2.0, automatically translated via the Google Translate API. Answer-span alignment errors caused by translation were corrected using fuzzy string matching. Evaluation was conducted under identical hyperparameter settings and training schemes, using Exact Match (EM) and F1-score as performance metrics. The results indicate that IndoLEM achieved superior performance, with better loss convergence and a higher F1-score (71.58) than IndoNLU (63.59), and the difference was statistically significant (p < 0.001). In conclusion, IndoLEM is a more effective baseline model for Indonesian extractive QA systems. The findings also demonstrate that the composition and scale of pre-trained corpora substantially influence model performance in low-resource language contexts and highlight the importance of transfer learning for advancing NLP in underrepresented languages.

The fast growing digital culture has attracted people’s attention and motivated them to interact with fascinating multimedia materials, including images, videos, voice notes and messages. Video is the most often used digital material format globally; it is used for marketing for companies, education, proof of concern, memorial ceremonies, and amusement among other purposes. The primary goal of video/image captioning is to represent the dynamics of a video clip using simple and understandable conversational language. The motivation for captioning comes from its ability to enhance video accessibility for those who are deaf or hard-of-hearing, improve concentration and memory of information and allow viewing in sound-sensitive environments. In this proposed framework, we demonstrate how to create captions for videos using Gated Recurrent Unit (GRU) along with a Sentence Vector Branch (SVB) and skip connections employing two word embedding methods: Bidirectional Encoder Representations from Transformers (BERT) and Embeddings from Language Model (ELMO). The encoder section of the model uses skip connections to address the issue of vanishing gradients and the sentence vector branch is used to improve the efficiency of the encoder-decoder architecture. The decoder generates a suitable description using the sentence vector branch together with past generated words. All of our experiments make use of the Standard MSVD databases. BLEU@4, METEOR, ROUGE and CIDEr measures have been applied for the performance assessment. Comparative analysis of BERT and ELMO word embeddings reveals their respective strengths. Features are extracted from pre-trained CNNs NASNet-Large, VGG16, Inceptionv3, DenseNet-169 and ResNet50. In the MSVD dataset, BERT beats ELMO in the case of the GRU-based model, whereas ELMO beats BERT in the case of the LSTM-based model; among LSTM and GRU, LSTM outperforms GRU. DenseNet-169 beats every feature extraction method used in the MSVD dataset.

Recently, people used social media to convey their emotions in the text. Text classification is required for group a text containing emotion or not and identify the type of emotion. Most of the research in emotion classification use machine learning methods. So this research offers the use of deep learning for the classification of emotions in text. One of the algorithms that is widely used for deep learning is BERT (Bidirectional Encoder Representations from Transformers). For the experiment, classification is divided into two phases, namely the first phase groups emotion or not emotion tweets, and the second phase groups emotion tweets into five types of emotions, namely happy, angry, sad, scared and surprised. The experiment uses three data scenarios, namely the commuter line, transjakarta and combination data. The BERT method was compared with the BiLSTM and LSTM methods for emotion classification. The result of this study is BERT generates the highest accuracy compared to other methods for the three data scenarios with values of 87.24%, 86.27%, and 86.99% in the first phase. Then, the next accuracy value followed by obtained BiLSTM, and the last is LSTM. In the second phase, BERT also obtained the highest accuracy values for the three data scenarios with values of 94.26%, 93.71 %, and 93.98%. Then, the evaluation using Precision, Recall and F1-Measure results that BERT provides the best overall method. In this study, BERT has good performance for emotion classification.

Multitask learning (MTL) and data augmentation are becoming increasingly popular in natural language processing (NLP). These techniques are particularly useful when data are scarce. In MTL, knowledge learned from one task is applied to another. To address data scarcity, data augmentation facilitates by providing additional synthetic data during model training. In NLP, the bidirectional encoder representations from transformers (BERT) model is the default candidate for various tasks. MTL and data augmentation using BERT have yielded promising results. However, a detailed study regarding the effect of using MTL in different layers of BERT and the benefit of data augmentation in these configurations has not been conducted. In this study, we investigate the use of MTL and data augmentation from generative models, specifically for category classification, sentiment classification, and aspect-opinion sequence-labeling using BERT. The layers of BERT are categorized into top, middle, and bottom layers, which are frozen, shared, or unshared. Experiments are conducted to identify the optimal layer configuration for improved performance compared with that of single-task learning. Generative models are used to generate augmented data, and experiments are performed to reveal their effectiveness. The results indicate the effectiveness of the MTL configuration compared with single-task learning as well as the effectiveness of data augmentation using generative models for classification tasks.

Natural Language Processing (NLP) is a pivotal area in artificial intelligence, aiming to make computers capable of understanding and generating human language. This study evaluates and compares three prominent NLP models—the Generative Pre-trained Transformer (GPT) model, Bidirectional Encoder Representations from Transformers (BERT) model, and Generalized Autoregressive Pretraining for Language Understanding (XLNet)—to determine their strengths, limitations, and suitability for various tasks. The research involves a comprehensive analysis of these models, utilizing well-established datasets such as the Stanford Question Answering Dataset (SQuAD), General Language Understanding Evaluation (GLUE), Reading Comprehension from Examinations (RACE), and the Situations with Adversarial Generations (SWAG). The study explores each model's architecture, pre-training, and fine-tuning processes: GPT’s unidirectional approach is assessed for its language generation and handling of long-range dependencies; Bidirectional encoding is examined for its effectiveness in context understanding, and XLNet permutation-based training is analyzed for its robust contextual comprehension. The experimental results reveal that GPT excels in generative tasks but is constrained by its unidirectional nature. BERT achieves superior accuracy in comprehension tasks but is computationally demanding and susceptible to pre-training bias. XLNet outperforms both GPT and BERT in accuracy and contextual understanding, though at the cost of increased complexity. The results offer a significant understanding of the effectiveness and applicability of these models, suggesting future research directions such as hybrid models and improvements in efficiency.